© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 67407
    Prev
    Next
    INDEX
    Explanations

    directy improvement

    np_acts-logits-general · gemini-2.5-flash-lite

    determine, requires, means

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ام
    0.50
    am
    0.48
    ب
    0.47
    วัน
    0.47
    in
    0.47
    ch
    0.46
    다
    0.46
    qu
    0.45
    าก
    0.45
    ق
    0.45
    POSITIVE LOGITS
    贻
    0.52
    Gé
    0.50
    萧
    0.49
     بسر
    0.48
    慝
    0.47
     thậm
    0.47
     তড়িৎ
    0.46
    厉
    0.46
     Lé
    0.46
    ——
    0.45
    Activations Density 0.001%

    No Known Activations